© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39745
    Prev
    Next
    INDEX
    Explanations

    how something functions or leads to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»Ģä¹Īåij¢
    -0.09
    æĢİä¹ĪåĬŀåij¢
    -0.09
    ä¹ĭæīĢ以
    -0.08
     however
    -0.07
    åIJĹ
    -0.07
     which
    -0.07
     whoever
    -0.07
     therefore
    -0.07
     too
    -0.07
     because
    -0.07
    POSITIVE LOGITS
    以åıĬå¦Ĥä½ķ
    0.15
     ÙĪÙĥÙĬÙģ
    0.14
    à¸ļà¹īาà¸ĩ
    0.13
    çļĦåij¢
    0.10
    ä¸ĢæŃ¥æŃ¥
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    åıĪå¦Ĥä½ķ
    0.09
     concretamente
    0.08
    åıĪæĪĸèĢħ
    0.08
    å°±çŁ¥éģĵäºĨ
    0.08
    Activations Density 0.142%

    No Known Activations